API
-
concrete.ml.pytest.utils
: Common functions or lists for test files, which can't be put in fixtures. -
concrete.ml.quantization.base_quantized_op
: Base Quantized Op class that implements quantization for a float numpy op. -
concrete.ml.quantization.quantized_ops
: Quantized versions of the ONNX operators for post training quantization. -
concrete.ml.search_parameters.p_error_search
: p_error binary search for classification and regression tasks.
-
torch_models.MultiOpOnSingleInputConvNN
: Network that applies two quantized operations on a single input. -
torch_models.QNNFashionMNIST
: A small quantized network with Brevitas for FashionMNIST classification. -
torch_models.QuantCustomModel
: A small quantized network with Brevitas, trained on make_classification. -
torch_models.SingleMixNet
: Torch model that with a single conv layer that produces the output, eg a blur filter. -
torch_models.StepActivationModule
: Torch model implements a step function that needs Greater, Cast and Where. -
torch_models.TorchSumMod
: Torch model to test the ReduceSum ONNX operator in a circuit containing a PBS. -
base_quantized_op.QuantizedMixingOp
: An operator that mixes (adds or multiplies) together encrypted inputs. -
quantized_ops.QuantizedBatchNormalization
: Quantized Batch normalization with encrypted input and in-the-clear normalization params. -
p_error_search.BinarySearch
: Class forp_error
hyper-parameter search for classification and regression tasks. -
base.QuantizedTorchEstimatorMixin
: Mixin that provides quantization for a torch module and follows the Estimator API.
-
check_inputs.check_X_y_and_assert_multi_output
: sklearn.utils.check_X_y with an assert and multi-output handling. -
custom_assert.assert_not_reached
: Provide a custom assert to check that a piece of code is never reached. -
utils.check_there_is_no_p_error_options_in_configuration
: Check the user did not set p_error or global_p_error in configuration. -
utils.generate_proxy_function
: Generate a proxy function for a function accepting only *args type arguments. -
utils.get_model_class
: Return the class of the model (instantiated or not), which can be a partial() instance. -
utils.is_model_class_in_a_list
: Indicate if a model class, which can be a partial() instance, is an element of a_list. -
utils.manage_parameters_for_pbs_errors
: Return (p_error, global_p_error) that we want to give to Concrete. -
convert.get_equivalent_numpy_forward_and_onnx_model
: Get the numpy equivalent forward of the provided torch Module. -
onnx_impl_utils.compute_onnx_pool_padding
: Compute any additional padding needed to compute pooling layers. -
onnx_impl_utils.numpy_onnx_pad
: Pad a tensor according to ONNX spec, using an optional custom pad value. -
onnx_impl_utils.onnx_avgpool_compute_norm_const
: Compute the average pooling normalization constant. -
onnx_model_manipulations.clean_graph_after_node_op_type
: Clean the graph of the onnx model by removing nodes after the given node type. -
onnx_model_manipulations.clean_graph_at_node_op_type
: Clean the graph of the onnx model by removing nodes at the given node type. -
onnx_model_manipulations.keep_following_outputs_discard_others
: Keep the outputs given in outputs_to_keep and remove the others from the model. -
onnx_model_manipulations.remove_unused_constant_nodes
: Remove unused Constant nodes in the provided onnx model. -
onnx_model_manipulations.simplify_onnx_model
: Simplify an ONNX model, removes unused Constant nodes and Identity nodes. -
ops_impl.numpy_greater_float
: Compute greater in numpy according to ONNX spec and cast outputs to floats. -
ops_impl.numpy_greater_or_equal_float
: Compute greater or equal in numpy according to ONNX specs and cast outputs to floats. -
ops_impl.numpy_less_float
: Compute less in numpy according to ONNX spec and cast outputs to floats. -
ops_impl.numpy_less_or_equal_float
: Compute less or equal in numpy according to ONNX spec and cast outputs to floats. -
utils.get_random_extract_of_sklearn_models_and_datasets
: Return a random sublist of sklearn_models_and_datasets. -
p_error_search.compile_and_simulated_fhe_inference
: Get the quantized module of a given model in FHE, simulated or not. -
sklearn.get_sklearn_neural_net_models
: Return the list of available neural net models in Concrete ML. -
tree_to_numpy.workaround_squeeze_node_xgboost
: Workaround to fix torch issue that does not export the proper axis in the ONNX squeeze node. -
compile.convert_torch_tensor_or_numpy_array_to_numpy_array
: Convert a torch tensor or a numpy array to a numpy array.
Last modified 1mo ago